INDEX

Explanations

references to dates and possibly numbers, particularly in specific contexts related to time

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Numbers followed by counters or units

np_acts-logits-general · gemini-2.0-flash

numbers and dates

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.95

-0.84

-0.82

-0.81

-0.78

-0.74

-0.73

-0.72

-0.69

POSITIVE LOGITS

 eighty

1.08

 seventy

1.08

 forty

1.07

 ninety

1.07

 sixty

1.06

 fifty

1.03

 twenty

1.02

 thirty

0.98

 nineteen

0.96

 eighteen

0.95

Activations Density 0.167%

references to dates and possibly numbers, particularly in specific contexts related to time

Numbers followed by counters or units

numbers and dates

No Comments

No Known Activations